From 2c3617ad2d8a2ad98b573cc34483d1cb7cd451f5 Mon Sep 17 00:00:00 2001
From: Pierre Habouzit <madcoder@debian.org>
Date: Tue, 14 Nov 2006 23:40:36 +0100
Subject: [PATCH] use gperf for the charsets as well. we're more efficient
 *AND* more clever than the previous function.

Signed-off-by: Pierre Habouzit <madcoder@debian.org>
---
 Makefile.am |   6 +-
 charset.c   | 155 +++++-----------------------------------------------
 charset.def | 131 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 150 insertions(+), 142 deletions(-)
 create mode 100644 charset.def

diff --git a/Makefile.am b/Makefile.am
index 37aa605..f0dc512 100644
--- a/Makefile.am
+++ b/Makefile.am
@@ -13,7 +13,8 @@ SUBDIRS = intl m4 po $(XXXXXXXXXXXX_doc) contrib \
 	  lib-mime lib-lib lib-crypt lib-hash lib-sys lib-ui lib \
 	  pop imap $(NNTP_SUBDIR)
 
-BUILT_SOURCES = keymap_defs.h version.h
+BUILT_SOURCES = keymap_defs.h version.h charset.gperf
+DISTCLEANFILES = $(BUILT_SOURCES)
 
 bin_PROGRAMS = madmutt madmutt_dotlock pgpringng pgpewrapng smime_keysng
 madmutt_SOURCES = $(BUILT_SOURCES) \
@@ -96,6 +97,9 @@ LDADD = @LIBOBJS@ @LIBINTL@
 
 OPS=@OPS@
 
+charset.gperf: charset.def
+	sh $< > $@
+
 smime_keysng: $(srcdir)/smime_keys.pl
 	cp $(srcdir)/smime_keys.pl smime_keysng
 	chmod +x smime_keysng
diff --git a/charset.c b/charset.c
index bbaf8ca..544b357 100644
--- a/charset.c
+++ b/charset.c
@@ -40,126 +40,7 @@
 char *Charset;
 int Charset_is_utf8 = 0;
 
-/* 
- * The following list has been created manually from the data under:
- * http://www.isi.edu/in-notes/iana/assignments/character-sets
- * Last update: 2000-09-07
- *
- * Note that it includes only the subset of character sets for which
- * a preferred MIME name is given.
- */
-
-static struct {
-    const char *key;
-    const char *pref;
-} PreferredMIMENames[] = {
-    {"ansi_x3.4-1968", "us-ascii"},
-    {"iso-ir-6", "us-ascii"},
-    {"iso_646.irv:1991", "us-ascii"},
-    {"ascii", "us-ascii"},
-    {"iso646-us", "us-ascii"},
-    {"us", "us-ascii"},
-    {"ibm367", "us-ascii"},
-    {"cp367", "us-ascii"},
-    {"csascii", "us-ascii"},
-    {"csiso2022kr", "iso-2022-kr"},
-    {"cseuckr", "euc-kr"},
-    {"csiso2022jp", "iso-2022-jp"},
-    {"csiso2022jp2", "iso-2022-jp-2"},
-    {"iso_8859-1:1987", "iso-8859-1"},
-    {"iso-ir-100", "iso-8859-1"},
-    {"iso_8859-1", "iso-8859-1"},
-    {"latin1", "iso-8859-1"},
-    {"l1", "iso-8859-1"},
-    {"ibm819", "iso-8859-1"},
-    {"cp819", "iso-8859-1"},
-    {"csisolatin1", "iso-8859-1"},
-    {"iso_8859-2:1987", "iso-8859-2"},
-    {"iso-ir-101", "iso-8859-2"},
-    {"iso_8859-2", "iso-8859-2"},
-    {"latin2", "iso-8859-2"},
-    {"l2", "iso-8859-2"},
-    {"csisolatin2", "iso-8859-2"},
-    {"iso_8859-3:1988", "iso-8859-3"},
-    {"iso-ir-109", "iso-8859-3"},
-    {"iso_8859-3", "iso-8859-3"},
-    {"latin3", "iso-8859-3"},
-    {"l3", "iso-8859-3"},
-    {"csisolatin3", "iso-8859-3"},
-    {"iso_8859-4:1988", "iso-8859-4"},
-    {"iso-ir-110", "iso-8859-4"},
-    {"iso_8859-4", "iso-8859-4"},
-    {"latin4", "iso-8859-4"},
-    {"l4", "iso-8859-4"},
-    {"csisolatin4", "iso-8859-4"},
-    {"iso_8859-6:1987", "iso-8859-6"},
-    {"iso-ir-127", "iso-8859-6"},
-    {"iso_8859-6", "iso-8859-6"},
-    {"ecma-114", "iso-8859-6"},
-    {"asmo-708", "iso-8859-6"},
-    {"arabic", "iso-8859-6"},
-    {"csisolatinarabic", "iso-8859-6"},
-    {"iso_8859-7:1987", "iso-8859-7"},
-    {"iso-ir-126", "iso-8859-7"},
-    {"iso_8859-7", "iso-8859-7"},
-    {"elot_928", "iso-8859-7"},
-    {"ecma-118", "iso-8859-7"},
-    {"greek", "iso-8859-7"},
-    {"greek8", "iso-8859-7"},
-    {"csisolatingreek", "iso-8859-7"},
-    {"iso_8859-8:1988", "iso-8859-8"},
-    {"iso-ir-138", "iso-8859-8"},
-    {"iso_8859-8", "iso-8859-8"},
-    {"hebrew", "iso-8859-8"},
-    {"csisolatinhebrew", "iso-8859-8"},
-    {"iso_8859-5:1988", "iso-8859-5"},
-    {"iso-ir-144", "iso-8859-5"},
-    {"iso_8859-5", "iso-8859-5"},
-    {"cyrillic", "iso-8859-5"},
-    {"csisolatincyrillic", "iso8859-5"},
-    {"iso_8859-9:1989", "iso-8859-9"},
-    {"iso-ir-148", "iso-8859-9"},
-    {"iso_8859-9", "iso-8859-9"},
-    {"latin5", "iso-8859-9"},
-    {"l5", "iso-8859-9"},
-    {"csisolatin5", "iso-8859-9"},
-    {"iso_8859-10:1992", "iso-8859-10"},
-    {"iso-ir-157", "iso-8859-10"},
-    {"latin6", "iso-8859-10"},
-    {"l6", "iso-8859-10"},
-    {"csisolatin6", "iso-8859-10"},
-    {"cskoi8r", "koi8-r"},
-    {"ms_kanji", "shift_jis"},
-    {"csshiftjis", "shift_jis"},
-    {"extended_unix_code_packed_format_for_japanese", "euc-jp"},
-    {"cseucpkdfmtjapanese", "euc-jp"},
-    {"csgb2312", "gb2312"},
-    {"csbig5", "big5"},
-    /* end of official brain damage.
-       what follows has been taken * from glibc's localedata files.  */
-    {"iso_8859-13", "iso-8859-13"},
-    {"iso-ir-179", "iso-8859-13"},
-    {"latin7", "iso-8859-13"},
-    {"l7", "iso-8859-13"},
-    {"iso_8859-14", "iso-8859-14"},
-    {"latin8", "iso-8859-14"},
-    {"l8", "iso-8859-14"},
-    {"iso_8859-15", "iso-8859-15"},
-    {"latin9", "iso-8859-15"},
-    {"latin0", "iso-8859-15"},
-    {"iso_8859-16", "iso-8859-16"},
-    {"latin10", "iso-8859-16"},
-    {"646", "us-ascii"},
-    {"eucjp", "euc-jp"},
-    {"pck", "shift_jis"},
-    {"ko_kr-euc", "euc-kr"},
-    {"zh_tw-big5", "big5"},
-    {"sjis", "shift_jis"},
-    {"euc-jp-ms", "eucjp-ms"},
-    {NULL, NULL}
-};
-
-void mutt_set_langinfo_charset (void)
+void mutt_set_langinfo_charset(void)
 {
 #ifdef HAVE_LANGINFO_CODESET
     char buff[LONG_STRING];
@@ -174,36 +55,28 @@ void mutt_set_langinfo_charset (void)
         Charset = m_strdup("iso-8859-1");
 }
 
+#include "charset.gperf"
 
 void mutt_canonical_charset(char *dest, ssize_t dlen, const char *name)
 {
-    ssize_t i;
-    char *p;
+    const struct cset_pair *cp;
     char scratch[LONG_STRING];
+    int i;
 
-    m_strcpy(scratch, sizeof(scratch), name);
-    m_strtolower(scratch);
-
-    /* catch some common iso-8859-something misspellings */
-    if (!strncmp(scratch, "8859", 4)) {
-        snprintf(scratch, sizeof(scratch), "iso-8859-%s",
-                 name + 4 + (name[4] == '-'));
-        m_strtolower(scratch);
-    } else
-    if (!strncmp(scratch, "iso8859", 7)) {
-        snprintf(scratch, sizeof(scratch), "iso-8859-%s",
-                 name + 7 + (name[7] == '-'));
-        m_strtolower(scratch);
-    }
+    // canonize name: only keep a-z0-9 and dots, put into lowercase
+    for (i = 0; i < ssizeof(scratch); i++) {
+        if (isalnum(*name) || *name == '.') {
+            scratch[i++] = tolower((unsigned char)*name);
+        }
 
-    for (i = 0; PreferredMIMENames[i].key; i++) {
-        if (!strcmp(scratch, PreferredMIMENames[i].key)) {
-            m_strcpy(dest, dlen, PreferredMIMENames[i].pref);
-            return;
+        if (!*name || *name == ':') {
+            scratch[i] = '\0';
+            break;
         }
     }
 
-    m_strcpy(dest, dlen, scratch);
+    cp = mutt_canonical_charset_aux(scratch, strlen(scratch));
+    m_strcpy(dest, dlen, cp ? cp->pref : name);
 }
 
 static int mutt_chscmp(const char *s, const char *chs)
diff --git a/charset.def b/charset.def
new file mode 100644
index 0000000..fc6abba
--- /dev/null
+++ b/charset.def
@@ -0,0 +1,131 @@
+cat <<EOF | gperf -Nmutt_canonical_charset_aux -m16 -l -t -C -F", NULL"
+%{
+/*
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or (at
+ *  your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ *  MA 02110-1301, USA.
+ *
+ *  Copyright © 2006 Pierre Habouzit
+ */
+
+/*
+ * The following list has been created manually from the data under:
+ * http://www.isi.edu/in-notes/iana/assignments/character-sets
+ * Last update: 2000-09-07
+ *
+ * Note that it includes only the subset of character sets for which
+ * a preferred MIME name is given.
+ *
+ * the corespondance tries to resume from any brain dead way to write the
+ * encoding name, hence you have to pass a charset stripped from its '-' and
+ * '_' and truncated at the first ':' encountered.
+ */
+%}
+struct cset_pair { const char *name; const char *pref; };
+%%
+ansix3.41968, "us-ascii"
+arabic, "iso-8859-6"
+ascii, "us-ascii"
+asmo708, "iso-8859-6"
+cp367, "us-ascii"
+cp819, "iso-8859-1"
+csascii, "us-ascii"
+csbig5, "big5"
+cseuckr, "euc-kr"
+cseucpkdfmtjapanese, "euc-jp"
+csgb2312, "gb2312"
+csiso2022jp2, "iso-2022-jp-2"
+csiso2022jp, "iso-2022-jp"
+csiso2022kr, "iso-2022-kr"
+csisolatin1, "iso-8859-1"
+csisolatin2, "iso-8859-2"
+csisolatin3, "iso-8859-3"
+csisolatin4, "iso-8859-4"
+csisolatin5, "iso-8859-9"
+csisolatin6, "iso-8859-10"
+csisolatinarabic, "iso-8859-6"
+csisolatincyrillic, "iso8859-5"
+csisolatingreek, "iso-8859-7"
+csisolatinhebrew, "iso-8859-8"
+cskoi8r, "koi8-r"
+csshiftjis, "shift_jis"
+cyrillic, "iso-8859-5"
+ecma114, "iso-8859-6"
+ecma118, "iso-8859-7"
+elot928, "iso-8859-7"
+eucjp, "euc-jp"
+eucjpms, "eucjp-ms"
+extendedunixcodepackedformatforjapanese, "euc-jp"
+greek8, "iso-8859-7"
+greek, "iso-8859-7"
+hebrew, "iso-8859-8"
+ibm367, "us-ascii"
+ibm819, "iso-8859-1"
+iso646.irv, "us-ascii"
+iso646us, "us-ascii"
+iso885910, "iso-8859-10"
+iso885913, "iso-8859-13"
+iso885914, "iso-8859-14"
+iso885915, "iso-8859-15"
+iso885916, "iso-8859-16"
+iso88591, "iso-8859-1"
+iso88592, "iso-8859-2"
+iso88593, "iso-8859-3"
+iso88594, "iso-8859-4"
+iso88595, "iso-8859-5"
+iso88596, "iso-8859-6"
+iso88597, "iso-8859-7"
+iso88598, "iso-8859-8"
+iso88599, "iso-8859-9"
+isoir100, "iso-8859-1"
+isoir101, "iso-8859-2"
+isoir109, "iso-8859-3"
+isoir110, "iso-8859-4"
+isoir126, "iso-8859-7"
+isoir127, "iso-8859-6"
+isoir138, "iso-8859-8"
+isoir144, "iso-8859-5"
+isoir148, "iso-8859-9"
+isoir157, "iso-8859-10"
+isoir179, "iso-8859-13"
+isoir6, "us-ascii"
+kokreuc, "euc-kr"
+l1, "iso-8859-1"
+l2, "iso-8859-2"
+l3, "iso-8859-3"
+l4, "iso-8859-4"
+l5, "iso-8859-9"
+l6, "iso-8859-10"
+l7, "iso-8859-13"
+l8, "iso-8859-14"
+latin0, "iso-8859-15"
+latin1, "iso-8859-1"
+latin2, "iso-8859-2"
+latin3, "iso-8859-3"
+latin4, "iso-8859-4"
+latin5, "iso-8859-9"
+latin6, "iso-8859-10"
+latin7, "iso-8859-13"
+latin8, "iso-8859-14"
+latin9, "iso-8859-15"
+latin10, "iso-8859-16"
+mskanji, "shift_jis"
+pck, "shift_jis"
+sjis, "shift_jis"
+us, "us-ascii"
+zhtwbig5, "big5"
+646, "us-ascii"
+%%
+// vim:set ft=lex:
+EOF
-- 
2.20.1